@tea-agent/loop-agent 0.20.1-beta.0 → 0.21.0

package/dist/workflows/dag/workspace-checkpoint.js

@@ -0,0 +1,163 @@
+import { createHash } from "node:crypto";
+import { spawn } from "node:child_process";
+import { lstat, readFile, realpath } from "node:fs/promises";
+import path from "node:path";
+import { writeJsonAtomic } from "../../infrastructure/harness/atomic-write.js";
+/**
+ * Workspace checkpoint for DAG continuation safety.
+ * Proves current repo content matches parent terminal state before importing facts.
+ */
+export const WORKSPACE_CHECKPOINT_START_REL = ".runtime/workspace-checkpoint-start.json";
+export const WORKSPACE_CHECKPOINT_TERMINAL_REL = ".runtime/workspace-checkpoint-terminal.json";
+function sha256Hex(input) {
+    return createHash("sha256").update(input).digest("hex");
+}
+async function runGit(cwd, args) {
+    return new Promise((resolve, reject) => {
+        const child = spawn("git", args, {
+            cwd,
+            stdio: ["ignore", "pipe", "pipe"],
+        });
+        let stdout = "";
+        let stderr = "";
+        child.stdout.setEncoding("utf-8");
+        child.stderr.setEncoding("utf-8");
+        child.stdout.on("data", (chunk) => {
+            stdout += chunk;
+        });
+        child.stderr.on("data", (chunk) => {
+            stderr += chunk;
+        });
+        child.on("error", reject);
+        child.on("close", (code) => {
+            if (code === 0) {
+                resolve(stdout);
+                return;
+            }
+            reject(new Error(`git ${args.join(" ")} failed: ${stderr.trim() || stdout.trim()}`));
+        });
+    });
+}
+function normalizeGitPath(value) {
+    const target = value.includes(" -> ")
+        ? (value.split(" -> ").at(-1) ?? value)
+        : value;
+    return target.replace(/\\/g, "/").replace(/^\.\//, "");
+}
+function classifyPorcelainState(x, y) {
+    if (x === "?" || y === "?")
+        return "untracked";
+    if (x === "R" || y === "R")
+        return "renamed";
+    if (x === "D" || y === "D")
+        return "deleted";
+    if (x === "A" || y === "A")
+        return "added";
+    if (x === "M" || y === "M")
+        return "modified";
+    return "modified";
+}
+async function hashWorkspacePath(repoRoot, relPath, state) {
+    if (state === "deleted") {
+        return { contentSha256: sha256Hex(`deleted:${relPath}`) };
+    }
+    const abs = path.join(repoRoot, relPath);
+    try {
+        const st = await lstat(abs);
+        const mode = (st.mode & 0o777777).toString(8);
+        if (st.isSymbolicLink()) {
+            const target = await realpath(abs).catch(async () => {
+                const { readlink } = await import("node:fs/promises");
+                return readlink(abs);
+            });
+            return {
+                mode,
+                contentSha256: sha256Hex(`symlink:${relPath}->${target}`),
+            };
+        }
+        if (st.isDirectory()) {
+            // Submodule or directory entry — fingerprint via git ls-files / HEAD if possible.
+            return {
+                mode,
+                contentSha256: sha256Hex(`dir:${relPath}`),
+            };
+        }
+        const bytes = await readFile(abs);
+        return { mode, contentSha256: sha256Hex(bytes) };
+    }
+    catch {
+        return { contentSha256: sha256Hex(`missing:${relPath}`) };
+    }
+}
+function computeFingerprint(input) {
+    const payload = JSON.stringify({
+        gitHeadSha: input.gitHeadSha,
+        statusPorcelainSha256: input.statusPorcelainSha256,
+        changedPaths: input.changedPaths,
+    });
+    return sha256Hex(payload);
+}
+/**
+ * Capture a workspace checkpoint for the current working tree.
+ */
+export async function captureWorkspaceCheckpoint(repoRoot, options) {
+    const capturedAt = (options?.now ?? new Date()).toISOString();
+    const gitHeadSha = (await runGit(repoRoot, ["rev-parse", "HEAD"])).trim();
+    const porcelain = await runGit(repoRoot, [
+        "status",
+        "--porcelain=v1",
+        "--untracked-files=all",
+    ]);
+    const statusPorcelainSha256 = sha256Hex(porcelain);
+    const changedPaths = [];
+    for (const line of porcelain.split("\n")) {
+        const trimmed = line.trimEnd();
+        if (!trimmed)
+            continue;
+        const x = trimmed[0] ?? " ";
+        const y = trimmed[1] ?? " ";
+        const rawPath = trimmed.slice(3);
+        const relPath = normalizeGitPath(rawPath);
+        const state = classifyPorcelainState(x, y);
+        const hashed = await hashWorkspacePath(repoRoot, relPath, state);
+        changedPaths.push({
+            path: relPath,
+            state,
+            ...hashed,
+        });
+    }
+    changedPaths.sort((a, b) => a.path.localeCompare(b.path));
+    const fingerprint = computeFingerprint({
+        gitHeadSha,
+        statusPorcelainSha256,
+        changedPaths,
+    });
+    return {
+        schemaVersion: 1,
+        capturedAt,
+        gitHeadSha,
+        statusPorcelainSha256,
+        changedPaths,
+        fingerprint,
+    };
+}
+export async function writeWorkspaceCheckpoint(runDir, relPath, checkpoint) {
+    await writeJsonAtomic(path.join(runDir, relPath), checkpoint);
+}
+export async function readWorkspaceCheckpoint(runDir, relPath) {
+    try {
+        const raw = JSON.parse(await readFile(path.join(runDir, relPath), "utf8"));
+        if (raw?.schemaVersion !== 1 || typeof raw.fingerprint !== "string") {
+            return undefined;
+        }
+        return raw;
+    }
+    catch {
+        return undefined;
+    }
+}
+export function workspaceFingerprintsMatch(left, right) {
+    if (!left?.fingerprint || !right?.fingerprint)
+        return false;
+    return left.fingerprint === right.fingerprint;
+}

package/docs/README.md

@@ -52,16 +52,14 @@
 完整索引与归档策略见 `design/README.md`。下列为当前高频活入口：
 
 - `design/backend-test-workflow.md` — backend-test Markdown-first 8 节点流程、单次 pytest、run-owned artifacts 与 L-5
-- `design/frontend-mock-data-workflow.md` — 前端 Mock 节点、触发条件、规范证据与失败路由
-- `design/frontend-implementation-workflow.md` — 前端实现 / 评审 / 验证工作流
+- `design/frontend-implementation-workflow.md` — 前端实现 / 评审 / 验证工作流（含 Mock/API 策略、capability seed、verification bundle）
 - `design/dag-source-binding-and-recovery.md` — 新生成 DAG 的任务源绑定与中断恢复
 - `design/agent-worker-fullstack-workflow-integration.md` — workflow routing、Task Outcome、artifact-aware Ready、`fullstack-v1` 与 Verification Bundle
 - `design/fullstack-end-to-end-delivery-optimization-roadmap.md` — 全栈端到端优化收敛路线图（release train / Delivery / Final Verification）
-- `design/2026-07-22-console-observe-unified-operator-surface.md` — Observe 深度融合进 Console（Wave 1–3 已实现，目标 0.18.0）
-- `design/local-operator-console-from-pi-web.md` — Operator Console 设计输入；MVP 已随 `0.17.0`–`0.17.2` 发布；统一 surface 见上条
+- `design/local-operator-console-from-pi-web.md` — Operator Console 设计输入；MVP 已随 `0.17.0`–`0.17.2` 发布；统一 surface 设计已归档（见下）
 - `design/taskspec-to-loop-agent-mapping.md` — TaskSpec → loop-agent task 兼容契约（文档镜像；runtime 真源在代码）
 
-已实现且仅作历史说明的设计见 `design/archive/`（例如 `design/archive/2026-07-14-loop-agent-self-update-notifier.md`）。
+已实现且仅作历史说明的设计见 `design/archive/`（例如 `design/archive/2026-07-14-loop-agent-self-update-notifier.md`、`design/archive/2026-07-22-console-observe-unified-operator-surface.md`、`design/archive/2026-07-23-operator-task-rerun-and-node-retry.md`、`design/archive/frontend-mock-data-workflow.md`）。
 
 ## 进行中 / 近期完成
 
@@ -75,6 +73,8 @@
 
 完整 completed 列表与主题速览见 `exec-plans/completed/README.md`。近期高频归档：
 
+- `exec-plans/completed/2026-07-24-backend-test-request-response-logs-report-format.md` — pytest 请求/响应脱敏日志与第 7/8 节点报告版式；真实 `my-webapp` Campaign R04 8/8、17 passed
+- `exec-plans/completed/2026-07-23-backend-test-advisory-gates.md` — 第 4/6 节点改为非阻断 advisory：用例只强制前置条件/步骤/预期，第 6 节点只扫描 Markdown 映射脚本；真实 `my-webapp` Campaign R02 8/8、10 passed
 - `exec-plans/completed/2026-07-23-backend-test-human-readable-artifacts.md` — 中文 README/用例卡片、class-based pytest traceability 与逐条 self-contained HTML 报告；真实 `my-webapp` Campaign Round 04 8/8、16 passed
 - `exec-plans/completed/2026-07-22-backend-markdown-gate-fix.md` — backend-test Markdown gate、traceability、中文生成与真实 Campaign 收口
 - `exec-plans/completed/2026-07-22-backend-test-markdown-first-8-node.md` — backend-test Markdown-first 8 节点

package/docs/architecture/dag-execution.md

@@ -101,6 +101,17 @@ snapshot 与 controller identity 是两个不同冻结层，详见 `runtime-boun
 
 decision envelope 中的 **model verdict**（`decision` / `riskLevel` 等解析自文本）是 `advisoryOnly: true` 派生视图，**不**是完成权威（`facts-and-state.md`）。
 
+## 自适应 liveness（节点活动 vs runner lease）
+
+实现见 `src/workflows/dag/liveness-policy.ts` 与设计文档 `docs/design/dag-adaptive-liveness-and-supervision.md`。
+
+- **runner lease**（`runner.heartbeatAt`，约 15s）只证明 runner 进程事件循环；**不是** Pi meaningful progress。
+- **真实活动**：SDK provider/tool event 与 CLI stdout|stderr 刷新 provider/tool/output；attempt-fenced，旧 attempt 晚到事件 no-op。SDK noisy delta 只续租 transport watchdog，不刷新 meaningful progress。
+- **节点投影** `livenessStatus`：`active | quiet | suspected-stall | probing | needs-attention`。
+- **absolute max** 默认 4h wall clock（不可被空心跳续期）；历史 30 分钟不再是活跃 Pi 节点硬杀边界。
+- `assessDagRunLiveness` 在 lease 新鲜但无 meaningful activity 时返回 `node-quiet` / `suspected-stall` / `needs-attention`；doctor codes 含 `node-activity-quiet`、`node-activity-suspected-stall`、`node-needs-attention`。
+- Observe/read-model 仅为 derived/advisory。
+
 ## 生命周期：active / paused / completed
 
 `src/workflows/dag/lifecycle.ts` 定义三个目录：

package/docs/architecture/facts-and-state.md

@@ -23,6 +23,7 @@
 - **Task Pool 是 Worker 专用可选根**：只有使用 `agent-worker` 产品线时才存在；唯一根 `.harness/task-pool/`。
 - **Task Pool state identity（ADR 0004）**：canonical 键为 `{ featureId, taskId }`（`TaskPoolTaskRef`），不是裸 `taskId`。
 - **Observe snapshot 不是事实源**：`buildGlobalSnapshot` 投影失败返回安全错误摘要而非全零健康，不改变执行成败。
+- **节点 liveness 投影是保守 canonical 字段**：`lastProviderActivityAt` / `lastToolActivityAt` / `lastOutputActivityAt` / `lastMeaningfulProgressAt` / `livenessStatus` 由 runner/executor 写入 active run facts；runner lease heartbeat **不得**刷新 meaningful progress。Observe badge（quiet/suspected-stall/needs-attention/needs-reconcile）仍是 derived。
 
 ### Task Pool state 布局与迁移
 

package/docs/architecture/worker-and-feature.md

@@ -17,6 +17,16 @@
 
 `shell: false` + 绝对 launch spec（见下）意味着 Worker 不走 PATH 重新解析，也不在当前进程内加载 CLI command 实现。
 
+### `run-dag` kernel-owned supervision vs explicit hard timeout
+
+`run-task` 启动 `run-dag` 时默认把外层 `timeoutMs` 设为 `0`，由 DAG kernel 负责节点 liveness，**不再**无条件把 30 分钟当作 hard kill：
+
+- 省略 `worker.timeout_ms` → Worker 不设置 wall-clock deadline，并等待 `run-dag` 产生可确认终态。
+- 显式 `worker.timeout_ms` → hard kill（可 capped），观察到 exit 后可报 `timedOut`。
+- 客户端 `onHeartbeat` 仍是监管心跳，不等于 Pi meaningful progress。
+
+设计真源：`docs/design/dag-adaptive-liveness-and-supervision.md`。
+
 ## controller identity（冻结的已发布 controller）
 
 每次写入型 Feature/batch/Task/final verification 在任何目标仓库或 Task Pool 状态写入前，`LoopAgentClient` 解析并冻结 schemaVersion 1 identity（`ControllerIdentityV1`，定义在 `src/shared/package-metadata.ts`）：

package/docs/templates/agent-dag.schema.json

@@ -402,10 +402,10 @@
         "retryCategories": {
           "type": "array",
           "items": {
-            "enum": ["timeout", "network", "rate-limit", "unavailable", "output-too-large"]
+            "enum": ["timeout", "network", "rate-limit", "unavailable", "output-too-large", "protocol-invalid"]
           },
           "default": ["timeout", "network", "rate-limit", "unavailable"],
-          "description": "Failure categories eligible for retry. quota is never eligible. output-too-large is reserved for explicit structured-required nodes and is not part of the default retry set."
+          "description": "Failure categories eligible for retry. quota is never eligible. output-too-large is reserved for explicit structured-required nodes. protocol-invalid is for nodes that declare outputProtocol with retryOnInvalid."
         }
       }
     },
@@ -496,6 +496,21 @@
           "minLength": 1,
           "description": "Optional protocol prefix whose first matching Pi assistant-output line is promoted to the canonical first line. Missing matches are not synthesized."
         },
+        "outputProtocol": {
+          "type": "object",
+          "additionalProperties": false,
+          "required": ["type", "validLines"],
+          "description": "Machine-readable output protocol for safe read-only Pi nodes. Phase 1 supports first-line-enum only (e.g. VERDICT lines). Invalid output may auto-retry when retryOnInvalid is true.",
+          "properties": {
+            "type": { "const": "first-line-enum" },
+            "validLines": {
+              "type": "array",
+              "items": { "type": "string", "minLength": 1 },
+              "minItems": 1
+            },
+            "retryOnInvalid": { "type": "boolean", "default": true }
+          }
+        },
         "allowedPaths": {
           "type": "array",
           "items": { "type": "string", "minLength": 1 },

package/docs/templates/backend-test-dag.generate-pytest.prompt.md

@@ -2,7 +2,7 @@
 
 ## Purpose
 
-供 `generate-backend-pytest-pi` 使用。该节点是 `executor: "pi"`、`role: "implementer"`、`toolProfile: "write"` 的受限 writer，只把已经通过 Markdown gate 的最终用例转换为 pytest 资产。
+供 `generate-backend-pytest-pi` 使用。该节点是 `executor: "pi"`、`role: "implementer"`、`toolProfile: "write"` 的受限 writer，只把经过独立 Review 和 advisory Markdown 校验的最终用例转换为 pytest 资产；第 4 节点报告为 FAIL 时仍继续，但不得据此发明缺失行为。
 
 ## 当前合同
 
@@ -19,7 +19,10 @@ class TestOrderApi:
         ...
 ```
 
-- 断言只来自 `### 预期结果` / `### Expected Results`；setup 只来自 `### 前置条件`、`### 测试数据`、`### 自动化映射` 或对应历史英文分节。
+- 断言只来自 `### 预期结果` / `### Expected Results`；setup 只来自必选 `### 前置条件`，以及存在时的 `### 测试数据`、`### 自动化映射` 或对应历史英文分节。
+- 每条可自动化 Case 应在 `自动化映射` / `Automation Notes` 明确写出目标 pytest 脚本；第 6 节点只扫描这些脚本，不递归扫描无关历史 `test_*.py`。
+- 每次接口请求必须通过统一日志 helper 或等价 client wrapper 打印请求与响应诊断信息：请求日志至少包含 HTTP method、URL/path、query 与 JSON/body/payload 参数摘要；响应日志至少包含 status code 与 JSON/text/body 结果摘要。日志必须能出现在 pytest stdout/stderr，不能改变断言或把失败伪装成通过。
+- 日志输出前必须递归脱敏 `authorization`、`proxy-authorization`、`cookie`、`set-cookie`、`token`、`password`、`secret`、`api key`、`credential` 等 key/header；禁止打印完整 Authorization/Cookie。序列化后的 request/response body 必须有明确长度上限和截断标识，避免大对象淹没 pytest/JUnit/报告证据。
 - 禁止 `skip` / `xfail`、吞断言、宽异常静默通过、mock 替代真实目标、删除用例或弱化断言。
 - best-effort 清理只能捕获所选 HTTP client 实际抛出的窄 transport exception，例如 `requests.RequestException` 或 `urllib.error.URLError`；禁止 `except:`、`except Exception`、`except BaseException` 后 `pass`。
 - 同一 Case ID 可以由多个 pytest 函数覆盖；额外映射会进入 traceability 报告，但不能伪造未在 Markdown 中定义的业务场景。

package/docs/templates/backend-test-dag.json

@@ -28,9 +28,9 @@
     "Root artifacts/ is reserved for explicit exclusive write nodes, not read-only scout/reviewer output",
     "exclusive implementer nodes must use narrow, concrete writeSet paths; never keep ** or repo root",
     "Replace REPLACE/WITH/NARROW/IMPLEMENT/PATHS/** with concrete paths before executing the implementation writer",
-    "backend-test-dag uses exactly 8 real top-level tasks and executes pytest exactly once.",
+    "backend-test-dag uses exactly 8 real top-level tasks and executes pytest exactly once over only the safe scripts explicitly mapped by final Markdown cases.",
     "Model nodes produce Markdown and pytest assets, never backend-test business JSON envelopes.",
-    "Environment, Markdown validation, traceability, JUnit, HTML and execution facts are deterministic fail-closed evidence.",
+    "Environment, advisory Markdown validation, advisory traceability, JUnit, HTML and execution facts are deterministic evidence. Nodes 4 and 6 record findings without blocking nodes 5, 7 or 8.",
     "Only Markdown case generation/review may read source facts; pytest generation must not read source/**.",
     "Functional case IDs use BE-<MODULE>-<NNN>; production code/config, skip/xfail, repair and rerun are forbidden."
   ],
@@ -68,8 +68,8 @@
   "executorModels": {
     "pi": {
       "LOW": "gpt-5.3-codex-spark",
-      "MED": "grok-4.5",
-      "HIGH": "gpt-5.6-sol"
+      "MED": "glm-5.2",
+      "HIGH": "gpt-5.5"
     }
   },
   "tasks": [
@@ -125,7 +125,7 @@
         "artifacts/**"
       ],
       "outputContract": "Write a Chinese, human-readable testcase/md/README.md plus module Markdown case cards using BE-<MODULE>-<NNN>; keep machine IDs/literals exact and do not execute pytest or modify production code/config.",
-      "subtask_prompt": "Read the upstream environment report. Generate a Markdown-first backend test strategy and cases under testcase/md/**.\n\nWrite human-readable content in Simplified Chinese by default. Keep English only for machine-readable IDs and technical literals such as Case/AC/REQ/BR IDs, HTTP methods, paths, field names, enum values, commands, filenames, code symbols and exact source citations.\n\nCreate testcase/md/README.md as the concise entry page: test objective, target/environment, isolation/cleanup, module summary and a linked case index table with Case ID, Chinese case name, scenario type, endpoint and expected status/result. Avoid repeating every case body in README.\n\nWrite each module as readable case cards. Every case starts with `## BE-<MODULE>-<NNN>｜<中文用例名称>` and uses these Chinese headings: `### 测试目的`, `### 验收标准`, `### 需求依据`, `### 前置条件`, optional `### 测试数据`, `### 操作步骤`, `### 预期结果`, and `### 自动化映射`. API metadata may use a compact table under the case heading. The deterministic validator also accepts legacy English headings, but new output should use this Chinese presentation.\n\nPlace steps and their expected results in a compact readable table when that improves clarity; otherwise keep numbered executable steps and numbered/bulleted independently assertable results. Every result must name the observable HTTP status, response field/value, state transition or membership condition, never vague wording such as ‘符合预期’.\n\nIn `自动化映射`, record the planned script path and pytest function name when known. Put implementation-only restrictions in a concise `<details>` block rather than dominating the main case flow. Use only environment-supported fixtures/targets/isolation, record evidence gaps in Chinese, and do not emit JSON, pytest, or execute commands.\n\n## Derived task contract: 需求.md\n\n# Backend test\n- AC-001 proof\n\n## Authoritative reference index\n\n[]\n\nFor each index entry, use `readPath` for Pi read-tool calls and copy `path` exactly into Markdown Source References. Bound files under .harness/tasks/<taskId>/source/** are read-only inputs: reading them is allowed even though writing .harness/** is forbidden. Never resolve `path` relative to the repository root, search for substitutes, or fall back to docs/** when a bound read fails.\n\nRead only precise indexed references needed for AC/API/field/rule evidence; references remain authoritative over derived text."
+      "subtask_prompt": "Read the upstream environment report. Generate a Markdown-first backend test strategy and cases under testcase/md/**.\n\nWrite human-readable content in Simplified Chinese by default. Keep English only for machine-readable IDs and technical literals such as Case/AC/REQ/BR IDs, HTTP methods, paths, field names, enum values, commands, filenames, code symbols and exact source citations.\n\nCreate testcase/md/README.md as the concise entry page: test objective, target/environment, isolation/cleanup, module summary and a linked case index table with Case ID, Chinese case name, scenario type, endpoint and expected status/result. Avoid repeating every case body in README.\n\nWrite each module as readable case cards. Every case starts with `## BE-<MODULE>-<NNN>｜<中文用例名称>`. The only sections required by the deterministic validator are `### 前置条件`, `### 操作步骤`, and `### 预期结果` (legacy English aliases remain accepted). Add `测试目的`, `验收标准`, `需求依据`, `测试数据`, and `自动化映射` when useful for human readability; every automatable case should explicitly name its target pytest script under `自动化映射` so traceability can scan only that script.\n\nPlace steps and their expected results in a compact readable table when that improves clarity; otherwise keep numbered executable steps and numbered/bulleted independently assertable results. Every result must name the observable HTTP status, response field/value, state transition or membership condition, never vague wording such as ‘符合预期’.\n\nIn `自动化映射`, record the planned script path and pytest function name when known. Put implementation-only restrictions in a concise `<details>` block rather than dominating the main case flow. Use only environment-supported fixtures/targets/isolation, record evidence gaps in Chinese, and do not emit JSON, pytest, or execute commands.\n\n## Derived task contract: 需求.md\n\n# Backend test\n- AC-001 proof\n\n## Authoritative reference index\n\n[]\n\nFor each index entry, use `readPath` for Pi read-tool calls and copy `path` exactly into Markdown Source References. Bound files under .harness/tasks/<taskId>/source/** are read-only inputs: reading them is allowed even though writing .harness/** is forbidden. Never resolve `path` relative to the repository root, search for substitutes, or fall back to docs/** when a bound read fails.\n\nRead only precise indexed references needed for AC/API/field/rule evidence; references remain authoritative over derived text."
     },
     {
       "id": "review-and-revise-backend-md-cases-pi",
@@ -149,7 +149,7 @@
         "artifacts/**"
       ],
       "outputContract": "Review source fidelity and directly revise only testcase/md/**; return concise Markdown, never JSON.",
-      "subtask_prompt": "Independently review generated Markdown cases against each case 需求依据 and environment evidence. Treat the files as human-facing test documentation: require a clear Chinese name and scenario/purpose, compact metadata, readable steps/results, and a concise automation mapping while preserving exact machine IDs and technical literals.\n\nCheck AC completeness/meaning, endpoint, fields/shape, status/error codes, rules, states, documented boundaries/auth, positive/negative coverage, executable steps and assertable results. Reject avoidable English prose, duplicated bilingual wording, repeated boilerplate, oversized unstructured sections, vague results such as ‘符合预期’, and missing script/function mapping where it can be derived.\n\nCorrect testcase/md/** directly: add documented omissions, remove unsupported cases, fix mappings/expectations, merge duplicates, improve navigation/tables/Chinese wording, or record gaps in Chinese. Keep Case IDs, AC/REQ/BR IDs, HTTP methods, paths, fields, enum values, filenames, code symbols and source citations exact. The validator accepts Chinese and legacy English section aliases; retain or converge to the Chinese human-readable headings without losing structure.\n\nRead only precise referenced source paths plus requirement sections needed for uncovered ACs. Do not scan the repository, modify source/**, generate pytest, execute tests, or emit JSON.\n\n## Derived task contract: 需求.md\n\n# Backend test\n- AC-001 proof\n\n## Authoritative reference index\n\n[]\n\nFor each index entry, use `readPath` for Pi read-tool calls and keep `path` as the exact Markdown Source References citation. Bound files under .harness/tasks/<taskId>/source/** are read-only inputs: reading them is allowed even though writing .harness/** is forbidden. Never resolve `path` relative to the repository root, search for substitutes, or fall back to docs/** when a bound read fails."
+      "subtask_prompt": "Independently review generated Markdown cases against the task requirements and environment evidence. Treat the files as human-facing test documentation: require clear preconditions, executable steps and assertable expected results; improve names, purpose, metadata and automation mapping where useful while preserving exact machine IDs and technical literals.\n\nCheck AC completeness/meaning, endpoint, fields/shape, status/error codes, rules, states, documented boundaries/auth, positive/negative coverage, executable steps and assertable results. Reject avoidable English prose, duplicated bilingual wording, repeated boilerplate, oversized unstructured sections, vague results such as ‘符合预期’, and missing script/function mapping where it can be derived.\n\nCorrect testcase/md/** directly: add documented omissions, remove unsupported cases, fix mappings/expectations, merge duplicates, improve navigation/tables/Chinese wording, or record gaps in Chinese. Keep Case IDs, AC/REQ/BR IDs, HTTP methods, paths, fields, enum values, filenames, code symbols and source citations exact. The validator accepts Chinese and legacy English section aliases; retain or converge to the Chinese human-readable headings without losing structure.\n\nRead only precise referenced source paths plus requirement sections needed for uncovered ACs. Do not scan the repository, modify source/**, generate pytest, execute tests, or emit JSON.\n\n## Derived task contract: 需求.md\n\n# Backend test\n- AC-001 proof\n\n## Authoritative reference index\n\n[]\n\nFor each index entry, use `readPath` for Pi read-tool calls and keep `path` as the exact Markdown Source References citation. Bound files under .harness/tasks/<taskId>/source/** are read-only inputs: reading them is allowed even though writing .harness/** is forbidden. Never resolve `path` relative to the repository root, search for substitutes, or fall back to docs/** when a bound read fails."
     },
     {
       "id": "validate-backend-md-cases-shell",
@@ -169,8 +169,8 @@
         ".harness/dag-runs/**",
         "artifacts/**"
       ],
-      "outputContract": "Run-owned reports/backend-md-case-validation.md proving final Markdown quality and safety.",
-      "subtask_prompt": "Fail closed on missing/duplicate IDs, sections, AC coverage, source references, executable steps, assertable results, placeholders or secret-shaped content.",
+      "outputContract": "Run-owned reports/backend-md-case-validation.md with PASS/FAIL advisory findings; downstream execution continues.",
+      "subtask_prompt": "Record advisory findings for missing/duplicate IDs, missing core sections (preconditions, steps, expected results), AC coverage, executable steps, assertable results or placeholders. Do not validate source-reference existence. Keep quality findings advisory, but fail closed after writing the report when secret-shaped values are detected so downstream pytest/report nodes cannot consume them.",
       "shell": {
         "commands": [],
         "backendTestPipeline": "markdown-cases",
@@ -203,7 +203,7 @@
         "artifacts/**"
       ],
       "outputContract": "Convert every final automatable Markdown case into pytest assets whose actual test function region contains the exact Case ID, preferably in the function name or docstring; no JSON and no pytest execution.",
-      "subtask_prompt": "Convert validated testcase/md/** to pytest using upstream environment and validation evidence plus only bounded pytest config/conftest.\n\nEnsure every final Markdown Case ID appears in at least one real pytest test function or pytest test class method region, preferably as `test_BE_<MODULE>_<NNN>_<description>` and in that function/method docstring. Module-level functions and class-based pytest methods are both supported. Multiple test functions may cover one Case ID; assertions come only from 预期结果/Expected Results and setup comes only from 前置条件/测试数据/自动化映射 or their legacy English aliases.\n\nDo not read source/**, add cases, reassign ACs, modify conftest/config/production code, use skip/xfail, swallow assertions, execute pytest, or emit JSON. For best-effort cleanup, catch only the narrow transport exception actually raised by the selected HTTP client (for example `requests.RequestException` or `urllib.error.URLError`); never use bare `except`, `Exception`, or `BaseException` with `pass`."
+      "subtask_prompt": "Convert testcase/md/** to pytest using upstream environment and advisory validation evidence plus only bounded pytest config/conftest. A FAIL advisory report does not authorize inventing missing behavior; use the final Markdown facts that are present.\n\nEnsure every final Markdown Case ID appears in at least one real pytest test function or pytest test class method region, preferably as `test_BE_<MODULE>_<NNN>_<description>` and in that function/method docstring. Module-level functions and class-based pytest methods are both supported. Multiple test functions may cover one Case ID; assertions come only from 预期结果/Expected Results and setup comes only from 前置条件 plus any optional 测试数据/自动化映射 or their legacy English aliases.\n\nGenerate a reusable HTTP logging helper (or equivalent client wrapper) and call it for every interface request. The request log must include method, URL/path, and request parameters (query plus JSON/body/payload summary). The response log must include status code and response result (JSON/text/body summary), and both records must be visible in pytest stdout/stderr without changing assertions.\n\nCompare timestamps and other semantically equivalent protocol values by parsed meaning, not byte-for-byte serialization. In particular, normalize valid ISO-8601 instants before equality/order assertions so differences such as omitted trailing fractional seconds do not create TestBug failures; preserve exact-string assertions only when the Markdown explicitly requires representation equality.\n\nBefore logging, recursively redact sensitive keys and header values including authorization, proxy-authorization, cookie, set-cookie, token, password, secret, api key and credentials. Never print full Authorization/Cookie values. Apply bounded truncation to serialized request and response bodies (with an explicit truncation marker) so large payloads cannot flood pytest or report artifacts.\n\nDo not read source/**, add cases, reassign ACs, modify conftest/config/production code, use skip/xfail, swallow assertions, execute pytest, or emit JSON. For best-effort cleanup, catch only the narrow transport exception actually raised by the selected HTTP client (for example `requests.RequestException` or `urllib.error.URLError`); never use bare `except`, `Exception`, or `BaseException` with `pass`."
     },
     {
       "id": "backend-test-traceability-gate-shell",
@@ -223,8 +223,8 @@
         ".harness/dag-runs/**",
         "artifacts/**"
       ],
-      "outputContract": "Run-owned reports/backend-test-traceability.md proving every real Markdown Case ID is covered by at least one pytest test function.",
-      "subtask_prompt": "Fail closed only when a real Markdown case heading has no associated pytest test function or class method. Accept exact Case IDs in the function/method name or its decorator/body/docstring region; report multiple mappings and extra automation Case IDs without blocking. Continue to reject skip/xfail or swallowed exceptions.",
+      "outputContract": "Run-owned reports/backend-test-traceability.md with PASS/FAIL advisory findings for Markdown Case to mapped pytest script/symbol coverage.",
+      "subtask_prompt": "Record advisory findings when a real Markdown case heading has no associated pytest test function or class method in the script explicitly mapped by that Markdown case, or when a mapped HTTP test script lacks request parameters logging, response result logging, recursive redaction or bounded truncation evidence. Accept exact Case IDs in the function/method name or its decorator/body/docstring region. Do not scan unrelated test_*.py files and do not block pytest execution.",
       "shell": {
         "commands": [],
         "backendTestPipeline": "markdown-traceability",
@@ -250,11 +250,11 @@
         ".harness/dag-runs/**",
         "artifacts/**"
       ],
-      "outputContract": "One pytest execution producing valid JUnit, self-contained HTML and reports/backend-test-facts.md; exit 0/1 with valid evidence continues.",
-      "subtask_prompt": "Execute pytest exactly once. Validate JUnit, render the primary self-contained Chinese HTML report from the same JUnit plus final Markdown case metadata without rerun, list every case with name/scenario/script/function/result/duration, and preserve failure summaries plus expandable technical details as facts.",
+      "outputContract": "One scoped pytest execution over Markdown-mapped scripts producing valid JUnit with per-case captured output, self-contained HTML and reports/backend-test-facts.md; exit 0/1 with valid evidence continues.",
+      "subtask_prompt": "Resolve the final Markdown Automation Notes/自动化映射 to a unique, safe set of testcase/**/test_*.py targets and execute only those scripts exactly once. Validate JUnit, then render the primary self-contained Chinese HTML report from the same JUnit plus final Markdown case metadata without rerun. Keep 测试结论, quality status, failure overview, and a polished per-case result card with concise scenario, automation test name, result, duration, and redacted bounded HTTP request parameters/response results for both passed and failed cases. Do not render a technical/execution evidence section in HTML; retain auditable paths and hashes in facts.",
       "shell": {
         "commands": [
-          "mkdir -p \"${HARNESS_DAG_RUN_DIR}/reports\"; PYTHONUTF8=1 PYTHONIOENCODING=utf-8 PYTHONDONTWRITEBYTECODE=1 python -m pytest testcase/ -v -p no:cacheprovider --junitxml=\"${HARNESS_DAG_RUN_DIR}/reports/backend-test.junit.xml\"; STATUS=$?; printf \"%s\" \"${STATUS}\" > \"${HARNESS_DAG_RUN_DIR}/reports/backend-test-pytest-exit.txt\"; if { [ \"${STATUS}\" -eq 0 ] || [ \"${STATUS}\" -eq 1 ]; } && [ -s \"${HARNESS_DAG_RUN_DIR}/reports/backend-test.junit.xml\" ]; then exit 0; fi; exit \"${STATUS}\""
+          "mkdir -p \"${HARNESS_DAG_RUN_DIR}/reports\"; echo \"pytest targets are resolved at runtime from final Markdown 自动化映射\""
         ],
         "backendTestPipeline": "markdown-execute-html",
         "cwd": ".",
@@ -284,7 +284,7 @@
         "artifacts/**"
       ],
       "outputContract": "Final Markdown report and L-5 conclusion under docs/test-reports/**; no JSON.",
-      "subtask_prompt": "Generate the final Markdown report from upstream facts and run-owned environment, case-validation, traceability, JUnit and HTML evidence. Do not emit JSON.\n\nInclude environment, case quality/review, automation mapping, exact pytest facts, failure classification/analysis, risks, regression recommendations, evidence paths/hashes, coverage/stability availability, and L-5 READY/NOT READY.\n\nNever override Shell/JUnit facts. One run cannot prove FlakyTest. Missing coverage/stability is Unavailable. L-5 requires pass=100%, AC=100%, automation>=90%, stability>=95% n>=5, line>=80%, branch>=70%, skipped=0 and no blocking Critical risk.\n\nWrite only under docs/test-reports/**."
+      "subtask_prompt": "Generate the final Markdown report from upstream facts and run-owned environment, advisory case-validation, advisory traceability, JUnit and HTML evidence. Do not emit JSON.\n\nUse this exact human-facing section order: 测试结论 → 执行概览 → 质量校验 → 失败分析 → 风险与建议 → 证据与 L-5. Put the decision and key numbers first, use compact tables/bullets, and keep headings concise. Do not paste entire upstream reports, duplicate per-case tables already present in facts, or repeat the same evidence in multiple sections; link to paths/hashes and quote only the findings needed for the conclusion.\n\nAlways state the exact PASS/FAIL status and findings from nodes 4 and 6. Their FAIL status does not block pytest, but it must remain visible as a quality/traceability risk and must never be rewritten as PASS.\n\nInclude environment, case quality/review, automation mapping, exact pytest facts, failure classification/analysis, risks, regression recommendations, evidence paths/hashes, coverage/stability availability, and L-5 READY/NOT READY.\n\nNever override Shell/JUnit facts. One run cannot prove FlakyTest. Missing coverage/stability is Unavailable. L-5 requires pass=100%, AC=100%, automation>=90%, stability>=95% n>=5, line>=80%, branch>=70%, skipped=0 and no blocking Critical risk.\n\nWrite only under docs/test-reports/**."
     }
   ],
   "sourceBinding": {

package/docs/templates/frontend-test-case-checklist.md

@@ -9,9 +9,24 @@ LLM review (when `frontendTest.reviewMode=blocking`) must not invent blocking ru
 |---|---|
 | `open-prefix` | Each case body includes `playwright-cli open --browser=chrome --headed <absolute-http(s)-url>` |
 | `production-url` | Open URL must not look like a production host |
-| `ac-mapping` | Manifest entry has non-empty `acIds` |
+| `ac-mapping` | Manifest entry has non-empty `acIds` (**acceptance** ids, not case ids) |
+| `ac-id-shape` | Each `acIds[]` entry matches `AC-*` / `AC-FE-*` |
+| `ac-id-is-case` | `acIds` must not contain `FE-*` case ids |
+| `unknown-ac` | When task `sourceBinding.requirementIds` lists ACs, every `acIds` entry must be in that set |
+| `case-id-shape` | `caseId` matches `FE-<FEATURE>-<NNN>-...` (never `AC-FE-*`) |
+| `case-id-is-ac` | Do not use acceptance id as `caseId` / filename |
+| `case-path-mismatch` | `casePath === testcase/frontend/cases/{caseId}.md` |
 | `case-file-missing` | `casePath` exists |
 | `no-test-source` | Case text must not introduce pytest / Playwright test source (`pytest`, `playwright.test`, `@playwright/test`) |
+| `playwright-cli-only` | Case steps may only use repo skill `playwright-cli` declared commands; bare `playwright` / `npx playwright` / `playwright test` / `@playwright/test` / Node Playwright API are forbidden |
+
+### ID 对照（避免混用）
+
+| 字段 | 正确示例 | 错误示例 |
+|---|---|---|
+| `caseId` | `FE-LOGIN-001-core` | `AC-FE-001` |
+| `acIds` | `["AC-FE-001"]` | `["FE-LOGIN-001-core"]` |
+| 文件名 | `FE-LOGIN-001-core.md` | `AC-FE-001.md` |
 
 ## Non-blocking (notes only)
 

package/docs/templates/frontend-test-dag.generate-cases.prompt.md

@@ -1,8 +1,20 @@
 # Generate frontend functional cases
 
-Use `playwright-cli-case-generator`. Read only `testcase/frontend/rag/context.md`, `coverage-map.md`, and existing `testcase/frontend/cases/`; write only that cases directory. Produce Markdown cases, `index.md`, and schema-version-1 `manifest.json`. Do not generate pytest or Playwright source code.
+Use `playwright-cli-case-generator`. Read only `testcase/frontend/rag/context.md`, `coverage-map.md`, and existing `testcase/frontend/cases/`; write only that cases directory. Produce Markdown cases, `index.md`, and schema-version-1 `manifest.draft.json` (materialize promotes to `manifest.json`). Do not generate pytest or Playwright source code.
 
-Each case is independently executable and includes AC mapping, preconditions, cleanup, UI assertions, and its isolated evidence path. Use dimensions `core`, `boundary`, `flow`, or `backend`. Never guess API fields, constraints, SLA, credentials, or unrecorded data.
+## HARD ID contract (frequent failure)
+
+| Concept | Field | Shape | Example |
+|---|---|---|---|
+| Test case id | `caseId` + filename | `FE-<FEATURE>-<NNN>-<dimension>` | `FE-LOGIN-001-core` |
+| Acceptance criteria | `acIds[]` | `AC-FE-*` / `AC-*` | `AC-FE-001` |
+
+- **Never** set `caseId` to `AC-FE-001` or name the file `AC-FE-001.md`.
+- **Never** put `FE-LOGIN-001-core` into `acIds`.
+- `casePath` must be `testcase/frontend/cases/<caseId>.md`.
+- `evidenceDir` must be `testcase/frontend/evidence/<caseId>/`.
+
+Each case is independently executable and includes AC mapping (`acIds`), preconditions, cleanup, UI assertions, and its isolated evidence path. Use dimensions `core`, `boundary`, `flow`, or `backend`. Never guess API fields, constraints, SLA, credentials, or unrecorded data.
 
 Every case must use the **resolved** absolute base URL from `testcase/frontend/rag/context.md` (field `baseUrl` / base URL line). Do not leave a `<base-url>` placeholder. Resolution policy (already applied by retrieve-context): prefer `config.md` frontend URL; else default `http://localhost:5173`.
 
@@ -14,6 +26,18 @@ playwright-cli open --browser=chrome --headed <resolved-base-url-from-context.md
 
 Do not put a session flag before `open`. Every later Playwright CLI command must stay in that same default browser session: do **not** emit `-s=<case-id>`, `-s=...`, or assume an undocumented named-session binding.
 
+## playwright-cli-only (hard)
+
+Every browser step must use only commands declared by the repo-local `playwright-cli` skill. Forbidden with **no fallback**: bare `playwright`, `npx playwright`, `playwright test`, `@playwright/test`, Node Playwright API, or generating Playwright/Pytest source. If `playwright-cli` is unavailable, the case must require blocked evidence with `blockedReason: playwright-cli-unavailable` and must not open a browser.
+
+## U/D data ownership (hard for modify/delete)
+
+1. Only mutate data whose ownership is proven by the **current login identity** plus observable UI/API owner fields — never by name, guessed id, or list order alone.
+2. If the current user has no suitable data, create tagged, cleanable data in the current-user context, then modify/delete, then cleanup and verify cleanup.
+3. If safe create is impossible, only task-authorized Mock may construct data, and the case must label it as Mock (not real backend proof).
+4. If ownership is unverifiable and create/Mock are unavailable: require blocked evidence with one of `current-user-data-unavailable`, `data-ownership-unverifiable`, `safe-test-data-setup-unavailable` — never risk cross-user data.
+5. Never touch other users' data, shared fixtures, production data, or non-cleanable data.
+
 For every executable sub-scenario, state the fixture/reset operation, UI reset operation, a fresh snapshot before using element references, and the exact evidence write point. If the isolated environment is unavailable, require writing blocked evidence before any browser command; do not open or connect to a browser.
 
 Each case must require the executor to persist, even when blocked:

package/docs/templates/frontend-test-dag.json

@@ -15,7 +15,10 @@
     "Case children execute serially. Persist each case result, logs and browser evidence before the next child starts.",
     "A token threshold is a post-case stop check, not a model hard token cap; unstarted cases must be recorded as blocked: token-budget-exhausted.",
     "Default pipeline acceptance is the final retrospect report under testcase/frontend/reports/; case full green is optional quality (frontendTest.strictOutcomeGate).",
-    "Default frontendTest.reviewMode=off uses mechanical checklist-shell before materialize; set reviewMode=blocking for legacy dual LLM review gate."
+    "Default frontendTest.reviewMode=off uses mechanical checklist-shell before materialize; set reviewMode=blocking for legacy dual LLM review gate.",
+    "playwright-cli-only: generators and executors may call only skill-declared playwright-cli commands; bare playwright / npx playwright / @playwright/test / Playwright source are forbidden with no native Playwright fallback.",
+    "Environment preflight must curl-probe the frozen non-production baseUrl before generate; unreachable or curl-unavailable ends preflight as blocked (frontend-base-url-unreachable|curl-unavailable) so generate/map do not run.",
+    "U/D cases must prove current-user data ownership or create cleanable current-user data or authorized Mock; otherwise blocked (current-user-data-unavailable|data-ownership-unverifiable|safe-test-data-setup-unavailable) without cross-user mutation."
   ],
   "tasks": [
     {
@@ -24,7 +27,7 @@
       "executor": "pi",
       "role": "planner",
       "toolProfile": "write",
-      "complexity": "HIGH",
+      "complexity": "MED",
       "writePolicy": "exclusive",
       "writeSet": [
         "testcase/frontend/rag/**"
@@ -37,14 +40,43 @@
         ".harness/**",
         "artifacts/**"
       ],
-      "outputContract": "RAG context.md and coverage-map.md.",
+      "outputContract": "RAG context.md and coverage-map.md with baseUrl, baseUrlSource, environmentProbe=pending.",
       "subtask_prompt_markdown": "./frontend-test-dag.retrieve-context.prompt.md"
     },
     {
-      "id": "generate-frontend-functional-cases-pi",
+      "id": "materialize-frontend-test-execution-shell",
       "depends_on": [
         "retrieve-frontend-test-context-pi"
       ],
+      "executor": "shell",
+      "role": "verifier",
+      "complexity": "LOW",
+      "writePolicy": "exclusive",
+      "writeSet": [
+        "testcase/frontend/rag/**"
+      ],
+      "allowedPaths": [
+        "testcase/frontend/rag/**"
+      ],
+      "forbiddenPaths": [
+        ".harness/**",
+        "artifacts/**"
+      ],
+      "outputContract": "Fail-closed environment preflight: absolute non-production baseUrl + curl HTTP reachability; writes environmentProbe facts; unreachable => blockedReason frontend-base-url-unreachable (node ERROR so generate/map do not run).",
+      "subtask_prompt": "Parse frozen baseUrl from context.md (config.md preferred, else http://localhost:5173). Reject production / non-http(s). Probe with curl (HEAD then GET fallback; connect/max-time; no auth/cookie). 2xx/3xx => reachable and continue. 4xx/5xx/DNS/timeout/connection refused/TLS => blockedReason frontend-base-url-unreachable. Missing curl => blockedReason curl-unavailable. Do not start the app. Runtime hybrid generator embeds the authoritative probe script.",
+      "shell": {
+        "commands": [
+          "node -e \"console.log('template placeholder: runtime hybrid DAG embeds curl preflight; do not use this static command as source of truth')\""
+        ],
+        "cwd": ".",
+        "timeoutMs": 60000
+      }
+    },
+    {
+      "id": "generate-frontend-functional-cases-pi",
+      "depends_on": [
+        "materialize-frontend-test-execution-shell"
+      ],
       "executor": "pi",
       "role": "implementer",
       "toolProfile": "write",
@@ -202,7 +234,7 @@
       "dependsPolicy": "all-or-condition-skip"
     },
     {
-      "id": "materialize-frontend-case-manifest-shell",
+      "id": "frontend-case-checklist-shell",
       "depends_on": [
         "final-frontend-case-review-gate-shell"
       ],
@@ -210,6 +242,33 @@
       "role": "verifier",
       "complexity": "LOW",
       "writePolicy": "read-only",
+      "allowedPaths": [
+        "testcase/frontend/rag/**",
+        "testcase/frontend/cases/**"
+      ],
+      "forbiddenPaths": [
+        ".harness/**",
+        "artifacts/**"
+      ],
+      "outputContract": "Mechanical checklist: open-prefix, non-prod absolute URL, acIds, playwright-cli-only, no pytest/playwright test source; emit structured ruleId issues on failure.",
+      "subtask_prompt": "Scan generated cases/manifest against the shared blocking checklist. Runtime hybrid embeds the authoritative script.",
+      "shell": {
+        "commands": [
+          "node -e \"console.log('template placeholder: runtime hybrid embeds checklist')\""
+        ],
+        "cwd": ".",
+        "timeoutMs": 120000
+      }
+    },
+    {
+      "id": "materialize-frontend-case-manifest-shell",
+      "depends_on": [
+        "frontend-case-checklist-shell"
+      ],
+      "executor": "shell",
+      "role": "verifier",
+      "complexity": "LOW",
+      "writePolicy": "read-only",
       "allowedPaths": [
         "testcase/frontend/cases/**"
       ],
@@ -217,7 +276,7 @@
         ".harness/**",
         "artifacts/**"
       ],
-      "outputContract": "Validated frontend manifest payload { cases: [...] }; shell command echo is permitted only as the prefix before exactly one final JSON line.",
+      "outputContract": "Validated frontend manifest payload { cases: [...] }; ruleId-tagged fail-closed validation; atomically materialize testcase/frontend/cases/manifest.json via temp+rename then delete draft; stdout is exactly one final JSON line {cases}.",
       "subtask_prompt": "Validate and materialize the generated frontend case manifest.",
       "shell": {
         "commands": [